Grasper: A generalist pursuer for pursuit-evasion problems

• Main Authors: LI, Pengdeng, LI, Shuxin, WANG, Xinrun, CERNY, Jakub, ZHANG, Youzhi, McAleer, Stephen, CHAN, Hau, AN, Bo
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Generalizability; Hypernetwork; Multi-Agent Learning; Pre-training and Fine-tuning; Pursuit-Evasion Problems; Artificial Intelligence and Robotics; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/9130; https://ink.library.smu.edu.sg/context/sis_research/article/10133/viewcontent/p1147_pvoa_cc_by.pdf
• Institution: Singapore Management University

Pursuit-evasion games (PEGs) model interactions between a team of pursuers and an evader in graph-based environments such as urban street networks. Recent advancements have demonstrated the effectiveness of the pre-training and fine-tuning paradigm in Policy-Space Response Oracles (PSRO) to improve...